Run started 2026-10-18 06:56 UTC
· completed 07:01 UTC
Headline Metrics
A case passes when (Correctness or String in Response) and Relevance and Tools pass.
Scorers that had nothing to judge are ignored; cases where no scorer produced a result are
counted as no data and excluded from every pass rate.
First Token Time
Time to the first response token (TTFT) — how long before the user sees anything.
mean
78.45s
p50
79.39s
p90
113.64s
p99
166.06s
min
35.29s
max
171.89s
std
38.54s
First Insight Time
Time to the agent's first update, such as a tool call or a reasoning step.
mean
7.76s
p50
9.12s
p90
9.61s
p99
11.16s
min
3.78s
max
11.33s
std
2.63s
Case Duration
Wall-clock time the eval harness measured for the whole case, including scoring and gRPC overhead. Always at least the agent's own time_total.
mean
90.04s
p50
84.96s
p90
131.30s
p99
172.81s
min
44.21s
max
177.42s
std
38.19s
LLM Time
Total time inside LLM spans, summed across every LLM call in the case.
mean
55.33s
p50
50.34s
p90
55.98s
p99
130.84s
min
33.23s
max
139.16s
std
28.89s
Tool Time
Total time executing tools — database queries, API calls and the like.
mean
31.57s
p50
23.31s
p90
54.28s
p99
67.54s
min
4.11s
max
69.01s
std
22.19s
Other Time
Agent time outside the LLM and tools: orchestration overhead.
mean
0.40s
p50
0.00s
p90
1.21s
p99
1.25s
min
0.00s
max
1.25s
std
0.56s
LLM Time Share
LLM time as a percentage of the agent's total span duration. This is the spread of per-case percentages, not the run-level ratio.
mean
68.7%
p50
69.3%
p90
83.2%
p99
85.8%
min
48.0%
max
86.1%
std
13.7%
Tool Time Share
Tool time as a percentage of the agent's total span duration. This is the spread of per-case percentages, not the run-level ratio.
mean
35.6%
p50
29.2%
p90
59.1%
p99
59.8%
min
10.7%
max
59.9%
std
19.0%
Tool Calls
Number of tool spans the agent produced for the case.
mean
11.27
p50
9.00
p90
16.00
p99
18.70
min
7.00
max
19.00
std
3.85
sum
124.00
Total Tokens
LLM tokens consumed across every call in the case (prompt plus completion).